Tracking over many frames
So far we’ve only considered two frames
Basic extension to f frames
1.Select features in first frame
2.Given feature in frame i, compute position/deformation in i+1
3.Select more features if needed
4.i = i + 1
5.If i < f, go to step 2
Issues
•Discrete search vs. Lucas Kanade?
–depends on expected magnitude of motion
–discrete search is more flexible
•How often to update feature template?
–update often enough to compensate for distortion
–updating too often causes drift
•How big should search window be?
–too small:  lost features.  Too large:  slow